SharonTudi
commited on
End of training
Browse files- README.md +55 -55
- config.json +16 -15
- model.safetensors +2 -2
- runs/Jan22_10-45-09_e9a77ba5e600/events.out.tfevents.1705920321.e9a77ba5e600.245.0 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# DIALOGUE_one
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 1.
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -55,54 +55,54 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
| 1.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.0011 | 16.25 | 780 | 1.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.0008 | 21.25 | 1020 | 1.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.0007 | 23.75 | 1140 | 1.
|
96 |
-
| 0.0007 | 24.38 | 1170 | 1.
|
97 |
-
| 0.0007 | 25.0 | 1200 | 1.
|
98 |
-
| 0.0007 | 25.62 | 1230 | 1.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.0006 | 27.5 | 1320 | 1.
|
102 |
-
| 0.0006 | 28.12 | 1350 | 1.
|
103 |
-
| 0.0006 | 28.75 | 1380 | 1.
|
104 |
-
| 0.
|
105 |
-
| 0.0006 | 30.0 | 1440 | 1.
|
106 |
|
107 |
|
108 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: bert-base-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
18 |
|
19 |
# DIALOGUE_one
|
20 |
|
21 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.2331
|
24 |
+
- Precision: 0.7635
|
25 |
+
- Recall: 0.7632
|
26 |
+
- F1: 0.7625
|
27 |
+
- Accuracy: 0.7632
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 1.229 | 0.62 | 30 | 1.0350 | 0.5533 | 0.5526 | 0.4885 | 0.5526 |
|
59 |
+
| 0.865 | 1.25 | 60 | 0.7887 | 0.8236 | 0.7763 | 0.7723 | 0.7763 |
|
60 |
+
| 0.6577 | 1.88 | 90 | 0.6786 | 0.8159 | 0.7632 | 0.7509 | 0.7632 |
|
61 |
+
| 0.4934 | 2.5 | 120 | 0.5809 | 0.8732 | 0.8289 | 0.8263 | 0.8289 |
|
62 |
+
| 0.4062 | 3.12 | 150 | 0.5829 | 0.7959 | 0.7895 | 0.7904 | 0.7895 |
|
63 |
+
| 0.2879 | 3.75 | 180 | 0.6573 | 0.7914 | 0.7763 | 0.7767 | 0.7763 |
|
64 |
+
| 0.3208 | 4.38 | 210 | 0.6510 | 0.7684 | 0.7632 | 0.7632 | 0.7632 |
|
65 |
+
| 0.2356 | 5.0 | 240 | 0.7371 | 0.8324 | 0.8026 | 0.8035 | 0.8026 |
|
66 |
+
| 0.1637 | 5.62 | 270 | 0.6212 | 0.8561 | 0.8553 | 0.8548 | 0.8553 |
|
67 |
+
| 0.1117 | 6.25 | 300 | 0.6782 | 0.8318 | 0.8289 | 0.8295 | 0.8289 |
|
68 |
+
| 0.0484 | 6.88 | 330 | 0.8347 | 0.8217 | 0.8158 | 0.8159 | 0.8158 |
|
69 |
+
| 0.0563 | 7.5 | 360 | 0.8745 | 0.8017 | 0.7895 | 0.7922 | 0.7895 |
|
70 |
+
| 0.0385 | 8.12 | 390 | 0.7141 | 0.8390 | 0.8158 | 0.8173 | 0.8158 |
|
71 |
+
| 0.0418 | 8.75 | 420 | 1.0020 | 0.8341 | 0.8289 | 0.8293 | 0.8289 |
|
72 |
+
| 0.0423 | 9.38 | 450 | 0.8778 | 0.7639 | 0.7632 | 0.7630 | 0.7632 |
|
73 |
+
| 0.0193 | 10.0 | 480 | 0.9370 | 0.8255 | 0.8026 | 0.8048 | 0.8026 |
|
74 |
+
| 0.0131 | 10.62 | 510 | 1.0443 | 0.8037 | 0.7895 | 0.7908 | 0.7895 |
|
75 |
+
| 0.0143 | 11.25 | 540 | 0.9799 | 0.8390 | 0.8158 | 0.8173 | 0.8158 |
|
76 |
+
| 0.0111 | 11.88 | 570 | 1.1469 | 0.7656 | 0.7632 | 0.7626 | 0.7632 |
|
77 |
+
| 0.0033 | 12.5 | 600 | 0.9717 | 0.7477 | 0.75 | 0.7486 | 0.75 |
|
78 |
+
| 0.0016 | 13.12 | 630 | 1.0248 | 0.7809 | 0.7763 | 0.7773 | 0.7763 |
|
79 |
+
| 0.0028 | 13.75 | 660 | 1.4541 | 0.7514 | 0.75 | 0.7487 | 0.75 |
|
80 |
+
| 0.0045 | 14.38 | 690 | 1.2292 | 0.7656 | 0.7632 | 0.7626 | 0.7632 |
|
81 |
+
| 0.0013 | 15.0 | 720 | 1.2528 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
82 |
+
| 0.0011 | 15.62 | 750 | 1.2332 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
83 |
+
| 0.0011 | 16.25 | 780 | 1.2946 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
84 |
+
| 0.001 | 16.88 | 810 | 1.2817 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
85 |
+
| 0.001 | 17.5 | 840 | 1.2400 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
86 |
+
| 0.0011 | 18.12 | 870 | 1.5933 | 0.7385 | 0.7368 | 0.7323 | 0.7368 |
|
87 |
+
| 0.0009 | 18.75 | 900 | 1.4288 | 0.7385 | 0.7368 | 0.7323 | 0.7368 |
|
88 |
+
| 0.0008 | 19.38 | 930 | 1.2843 | 0.7656 | 0.7632 | 0.7626 | 0.7632 |
|
89 |
+
| 0.0008 | 20.0 | 960 | 1.2699 | 0.7656 | 0.7632 | 0.7626 | 0.7632 |
|
90 |
+
| 0.0008 | 20.62 | 990 | 1.2718 | 0.7656 | 0.7632 | 0.7626 | 0.7632 |
|
91 |
+
| 0.0008 | 21.25 | 1020 | 1.2456 | 0.7656 | 0.7632 | 0.7626 | 0.7632 |
|
92 |
+
| 0.0007 | 21.88 | 1050 | 1.2366 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
93 |
+
| 0.0007 | 22.5 | 1080 | 1.2430 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
94 |
+
| 0.0007 | 23.12 | 1110 | 1.2353 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
95 |
+
| 0.0007 | 23.75 | 1140 | 1.2345 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
96 |
+
| 0.0007 | 24.38 | 1170 | 1.2325 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
97 |
+
| 0.0007 | 25.0 | 1200 | 1.2283 | 0.7484 | 0.75 | 0.7484 | 0.75 |
|
98 |
+
| 0.0007 | 25.62 | 1230 | 1.2236 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
99 |
+
| 0.0006 | 26.25 | 1260 | 1.2247 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
100 |
+
| 0.0006 | 26.88 | 1290 | 1.2263 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
101 |
+
| 0.0006 | 27.5 | 1320 | 1.2286 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
102 |
+
| 0.0006 | 28.12 | 1350 | 1.2307 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
103 |
+
| 0.0006 | 28.75 | 1380 | 1.2322 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
104 |
+
| 0.0006 | 29.38 | 1410 | 1.2330 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
105 |
+
| 0.0006 | 30.0 | 1440 | 1.2331 | 0.7635 | 0.7632 | 0.7625 | 0.7632 |
|
106 |
|
107 |
|
108 |
### Framework versions
|
config.json
CHANGED
@@ -1,13 +1,14 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "Hospital-Inform",
|
13 |
"1": "Hospital-Request",
|
@@ -15,24 +16,24 @@
|
|
15 |
"3": "general-thank"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
|
|
18 |
"label2id": {
|
19 |
"LABEL_0": 0,
|
20 |
"LABEL_1": 1,
|
21 |
"LABEL_2": 2,
|
22 |
"LABEL_3": 3
|
23 |
},
|
|
|
24 |
"max_position_embeddings": 512,
|
25 |
-
"model_type": "
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"output_past": true,
|
29 |
"pad_token_id": 0,
|
|
|
30 |
"problem_type": "single_label_classification",
|
31 |
-
"qa_dropout": 0.1,
|
32 |
-
"seq_classif_dropout": 0.2,
|
33 |
-
"sinusoidal_pos_embds": false,
|
34 |
-
"tie_weights_": true,
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.36.2",
|
|
|
|
|
37 |
"vocab_size": 28996
|
38 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
|
|
3 |
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "Hospital-Inform",
|
14 |
"1": "Hospital-Request",
|
|
|
16 |
"3": "general-thank"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
"label2id": {
|
21 |
"LABEL_0": 0,
|
22 |
"LABEL_1": 1,
|
23 |
"LABEL_2": 2,
|
24 |
"LABEL_3": 3
|
25 |
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
"max_position_embeddings": 512,
|
28 |
+
"model_type": "bert",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
|
|
31 |
"pad_token_id": 0,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
34 |
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.36.2",
|
36 |
+
"type_vocab_size": 2,
|
37 |
+
"use_cache": true,
|
38 |
"vocab_size": 28996
|
39 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f289213bdf7cd4d47ef304341a3eedbae9d979a01cfb3a7f8903dd29ded6293a
|
3 |
+
size 433276920
|
runs/Jan22_10-45-09_e9a77ba5e600/events.out.tfevents.1705920321.e9a77ba5e600.245.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:241690c246e400054e33dac8d6feb885d61c89f060becaab3cdbcc40b4ce39fe
|
3 |
+
size 35043
|
tokenizer_config.json
CHANGED
@@ -52,6 +52,6 @@
|
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
-
"tokenizer_class": "
|
56 |
"unk_token": "[UNK]"
|
57 |
}
|
|
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
"unk_token": "[UNK]"
|
57 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88e2f7149f0d113e95e3b4cb9549c76b64e7d131377e2c6236f5b6794ea70371
|
3 |
size 4664
|